Rotor cage asymmetries cause disturbances of the flux pattern in induction machines. These non-uniform magnetic field components affect machine torque and stator terminal quantities and are thus detectable by monitoring systems. However, the impact of minor machine asymmetries on the overall machine behavior is quite small. This makes the separation of the fault specific signals out of commonly distorted measurement quantities a challenging task. In order to schedule maintenance faults should be detect in an early state of growth. Thus, any monitoring method should be very sensitive. The proposed "Vienna Method" fulfills both excellent noise immunity and high sensitivity. Simulation and experimental results from an industrial IGBT drive verify the validity of the approach and its superior properties. The technique is based on real time machine models. Up to now these models have been used for advanced machine control purposes only. However, the comparison of the two machine models outputs permits an insightful analysis of the faulty machine behavior too. Out of the knowledge of the model interaction with machine asymmetries the conjunction of the control structure with the real operational behavior of the machine can be concluded. This is due to the fact that the on-line machine models also form the basis for machine control. In the paper the induction machine behavior is investigated for constant Volts per Herz Control as well Indirect and Direct Field Oriented Control.
For a tribological experiment involving a steel shaft sliding in a self-lubricating bronze bearing, a semi-supervised machine learning method for the classification of the state of operation is proposed. During the translatory oscillating motion, the system may undergo different states of operation from normal to critical, showing self-recovering behaviour. A Random Forest classifier was trained on individual cycles from the lateral force data from four distinct experimental runs in order to distinguish between four states of operation. The labelling of the individual cycles proved to be crucial for a high prediction accuracy of the trained RF classifier. The proposed semi-supervised approach allows choosing within a range between automatically generated labels and full manual labelling by an expert user. The algorithm was at the current state used for ex post classification of the state of operation. Considering the results from the ex post analysis and providing a sufficiently sized training dataset, online classification of the state of operation of a system will be possible. This will allow taking active countermeasures to stabilise the system or to terminate the experiment before major damage occurs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.